On the Geo-Indicativeness of Non-Georeferenced Text

Authors

  • Benjamin Adams University of California, Santa Barbara
  • Krzysztof Janowicz University of California, Santa Barbara

DOI:

https://doi.org/10.1609/icwsm.v6i1.14309

Keywords:

Text mining, Topic modeling, Geographic information retrieval, Knowledge extraction, Spatial analysis, Location estimation

Abstract

Geographic location is a key component for information retrieval on the Web, recommendation systems in mobile computing and social networks, and place-based integration on the Linked Data cloud. Previous work has addressed how to estimate locations by named entity recognition, from images, and via structured data. In this paper, we estimate geographic regions from unstructured, non geo-referenced text by computing a probability distribution over the Earth's surface. Our methodology combines natural language processing, geostatistics, and a data-driven bottom-up semantics. We illustrate its potential for mapping geographic regions from non geo-referenced text.

Downloads

Published

2021-08-03

How to Cite

Adams, B., & Janowicz, K. (2021). On the Geo-Indicativeness of Non-Georeferenced Text. Proceedings of the International AAAI Conference on Web and Social Media, 6(1), 375-378. https://doi.org/10.1609/icwsm.v6i1.14309